15924 matches found
Model Poisoning against Federated Model Adaptation with Chain of Bit-Flips
Federated Learning FL allows a set of clients to collectively train a global model without sharing local training data. Giving the responsibility of the training to decentralized actors may lead to poisoning attacks: clients controlled by malicious third party potentially poison the training...
PT-2026-50613
OSS-Fuzz report: https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=520664955 Crash type: Heap-use-after-free READ 8 Crash state: lsr restore base lsr read polygon lsr read scene content model...
RECON: An LLM-Enhanced Backward Constraint Analysis Framework
While traditional techniques, such as symbolic execution, provide a principled foundation for precise constraint reasoning in program analysis, they struggle to scale to modern software systems mainly due to path explosion, the need for function modeling, and the loss of semantic intent at...
The vulnerability of the Model.load_model() function in the Keras library allows a hacker to execute arbitrary code.
The vulnerability of the Model.loadmodel function in the Keras library is related to deficiencies in the deserialization mechanism. Exploiting this vulnerability could allow a remote attacker to execute arbitrary code...
Steganography without Modification: Hidden Communication Via LLM Seeds
We demonstrate that widely deployed Large Language Model LLM inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions. The channel exploits a structural property of deterministic decoding: pseudo-random number generato...
RadKey: An LLM-Guided RF Backscatter System for Through-Wall Keystroke Inference
In today's digitally connected world, keyboards remain the primary interface for inputting sensitive information, making them a persistent target for eavesdropping attacks. While prior keystroke inference techniques have exploited side-channel signals such as acoustics and vibrations, they...
Customization under Fire: Plugin Poisoning in Text-To-Image Ecosystem
The prosperity of text-to-image T2I models has fostered a vibrant share-and-play ecosystem centered on Low-Rank Adaptation LoRA plugins, which allow users to customize and share model capabilities with ease. This democratization, however, comes with a hidden but severe security risk. Malicious...
TencentOS Server 4: python-django (TSSA-2026:0341)
The version of Tencent Linux installed on the remote TencentOS Server 4 host is prior to tested version. It is, therefore, affected by a vulnerability as referenced in the TSSA-2026:0341 advisory. Package updates are available for TencentOS Server 4 that fix the following vulnerabilities:...
CVE-2026-4944
A flaw was found in vllm-project/vllm. A hardcoded setting in the model implementation files bypasses the user's explicit security configuration, which is intended to prevent the execution of remote code. This allows a remote attacker to achieve remote code execution by providing a malicious mode...
MINI-MHJ4-RC4R-698M
Bulletin has no description...
MINI-H468-M389-GRF4
Bulletin has no description...
MINI-V378-HPC8-2VP4
Bulletin has no description...
MINI-M8MV-VWP7-6J95
Bulletin has no description...
MINI-Q432-4CMJ-MMW8
Bulletin has no description...
MINI-2MPF-P85P-QCXV
Bulletin has no description...
MINI-R98Q-234X-WR36
Bulletin has no description...
MINI-689F-689Q-65Q5
Bulletin has no description...